Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add OKHP3/skillz --skill okhp3-cowork-document-critiquegit clone --depth 1 https://github.com/OKHP3/skillzWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/okhp3/skillz/okhp3-cowork-document-critique)<a href="https://agentmods.dev/skills/okhp3/skillz/okhp3-cowork-document-critique"><img src="https://agentmods.dev/badge/skills/okhp3/skillz/okhp3-cowork-document-critique/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/okhp3/skillz/okhp3-cowork-document-critique"><img src="https://agentmods.dev/badge/skills/okhp3/skillz/okhp3-cowork-document-critique.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00068 | $0.01124 |
| Opus 5 | $0.00034 | $0.00562 |
| Sonnet 5 | $0.00014 | $0.00225 |
| Haiku 4.5 | $0.00007 | $0.00112 |
Grade A, and why
okhp3-cowork-document-critique scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
okhp3-cowork-document-critique
OverKill Hill P³ · overkillhill.com · github.com/OKHP3
Review the artifact against its job, not against generic prose preferences.
Scope
| In scope | Out of scope |
|---|---|
| Findings and draft revisions for a selected document against explicit criteria | Silent rewrites, publishing, sign-off, or unsupported legal/compliance conclusions |
Host contract
- Target: Microsoft Copilot Cowork personal custom skill.
- Portable core: assess a supplied draft against an audience, purpose, and observable rubric.
- Cowork adaptation: read a selected file only when it is available within the user's permissions and session context.
- Evidence: documented Cowork file-context behavior; no live package run.
Activation boundary and handoff
- Interactive and automation boundary: Use interactively by default. A scheduled or event-driven run may produce a draft only; it must not send, post, schedule, share, create, modify, move, rename, or delete anything.
- Approval policy: Require a current-session, target- and content-specific confirmation before an external action. This is this skill's policy, not a claim that Cowork enforces the same granularity.
- Portable fallback: Outside verified Cowork retrieval, use only material
supplied or attached by the user. Otherwise return
NEEDS INPUT; do not search local, tenant, or connector context. - Host availability: Cowork custom skills are not supported on mobile.
Return
NOT SUPPORTEDon an unavailable surface. A handoff guides work after activation; it cannot prove exclusive host skill selection. - Handoff: Use research evidence log when source-backed claims need review. Use an equilibrium review for a release-level independent assessment, not for this normal draft critique.
Required input and safe outcomes
Confirm the draft, audience, intended decision or action, quality criteria, and
review depth. Return NEEDS INPUT if audience or purpose is absent,
INSUFFICIENT PERMISSION if the file is unavailable, and NOT SUPPORTED if
the host cannot access or render the selected artifact.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 8d ago First seen · 108 lines · 68 tokens per session scan A 403ba678bf92
okhp3-cowork-document-critique is a skill published in the GitHub repository OKHP3/skillz (3 stars, last pushed today), licensed MIT. It adds 68 tokens to every session and 1,124 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
baoyu-youtube-transcript
A tool for downloading the written captions, subtitles, chapter information, speaker labels, and cover image from a YouTube video using its URL or ID.
baoyu-url-to-markdown
Fetch any URL and convert to markdown using baoyu-fetch CLI (Chrome CDP with site-specific adapters). Built-in adapters for X/Twitter, YouTube transcripts, Hacker News threads, and generic pages via Defuddle. Handles login/CAPTCHA via interaction wait modes. Use when user wants to save a webpage as markdown.
obsidian-markdown
A Markdown writing workflow for Obsidian, a note-taking app that can link notes together. It supports features such as two-way links, callouts, frontmatter, embedded content, and wikilinks.
obsidian-skills-integrated
A skill for writing and editing Obsidian notes while preserving Obsidian-specific formats. Obsidian is a note-taking app that supports links between notes, callouts, databases, and visual canvases.
pptx-generator
A tool that converts JSON data, a structured text format often used by software, into standard .pptx presentation files. It applies layouts and can format charts and tables.
pm-preview
A tool that previews Markdown product documents in a web browser and refreshes the view when the documents change. Markdown is a plain-text format commonly used for project documentation.